#wrangle to just variables for PCA and scale
penguin_pca <- penguins %>%
select(body_mass_g, ends_with("_mm")) %>%
drop_na() %>%
scale() %>%
prcomp()
penguin_pca$rotation #these are the loadings
## PC1 PC2 PC3 PC4
## body_mass_g 0.5483502 0.084362920 -0.5966001 -0.5798821
## bill_length_mm 0.4552503 0.597031143 0.6443012 -0.1455231
## bill_depth_mm -0.4003347 0.797766572 -0.4184272 0.1679860
## flipper_length_mm 0.5760133 0.002282201 -0.2320840 0.7837987
#need observations to match those of the PCS but still contain other variables (species)
penguin_complete <- penguins %>%
drop_na(body_mass_g, ends_with("_mm"))
#recognize type of data and assume what type of plot to make
autoplot(penguin_pca, data = penguin_complete,
colour = 'species',
loadings = TRUE,
loadings.label = TRUE) +
theme_minimal()
## Warning: `select_()` is deprecated as of dplyr 0.7.0.
## Please use `select()` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_warnings()` to see where this warning was generated.
fish_noaa <- read_excel(here::here("data","foss_landings.xlsx")) %>%
clean_names() %>%
mutate(across(where(is.character), tolower)) %>%
mutate(nmfs_name = str_sub(nmfs_name, end =-4)) %>%
filter(confidentiality == "public")
Make a customized graph:
fish_plot <- ggplot(data = fish_noaa, aes(x = year, y = pounds))+
geom_line(aes(color = nmfs_name), show.legend=FALSE) +
theme_minimal()
fish_plot
## Warning: Removed 6 row(s) containing missing values (geom_path).
ggplotly(fish_plot)
## Use gghighlight to highlight certain series
ggplot(data = fish_noaa, aes(x = year, y = pounds, group = nmfs_name))+
geom_line(aes(color = nmfs_name)) +
theme_minimal()+
gghighlight(max(pounds) > 1e8)
## label_key: nmfs_name
## Warning: Removed 6 row(s) containing missing values (geom_path).
lubridate(), mutate(), make months in logical ordermonroe_wt <- read_csv("https://data.bloomington.in.gov/dataset/2c81cfe3-62c2-46ed-8fcf-83c1880301d1/resource/13c8f7aa-af51-4008-80a9-56415c7c931e/download/mwtpdailyelectricitybclear.csv") %>%
clean_names()
## Parsed with column specification:
## cols(
## date = col_character(),
## kWh1 = col_double(),
## kW1 = col_double(),
## kWh2 = col_double(),
## kW2 = col_double(),
## solar_kWh = col_double(),
## total_kWh = col_double(),
## MG = col_double()
## )
monroe_ts <- monroe_wt %>%
mutate(date = mdy(date)) %>%
mutate(record_month = month(date)) %>%
mutate(month_name = month.abb[record_month]) %>%
mutate(month_name = fct_reorder(month_name, record_month))
ggplot(data = monroe_ts, aes(x = month_name, y = total_k_wh))+
geom_jitter()
#month.name is full name
patchworkgraph_a <- ggplot(data=penguins, aes(x=body_mass_g, y= flipper_length_mm))+
geom_point()
graph_b <- ggplot(data = penguins, aes(x=species, y=flipper_length_mm))+
geom_jitter(aes(color=species), show.legend=FALSE)
graph_c <- (graph_a | graph_b)/fish_plot & theme_dark()
graph_c
## Warning: Removed 2 rows containing missing values (geom_point).
## Warning: Removed 2 rows containing missing values (geom_point).
## Warning: Removed 6 row(s) containing missing values (geom_path).
ggsave(here::here("fig","graph_c_lk.png"), width = 5, height = 6)
## Warning: Removed 2 rows containing missing values (geom_point).
## Warning: Removed 2 rows containing missing values (geom_point).
## Warning: Removed 6 row(s) containing missing values (geom_path).